Major Enhancements:

- Installation path is now fully configurable, allowing users to specify custom installation directories during setup
  - Default installation location changed to .bmad (hidden directory) for cleaner project root organization

    Web Bundle Improvements:

    - All web bundles (single agent and team) now include party mode support for multi-agent collaboration!
    - Advanced elicitation capabilities integrated into standalone agents
    - All bundles enhanced with party mode agent manifests
    - Added default-party.csv files to bmm, bmgd, and cis module teams
    - The default party file is what will be used with single agent bundles. teams can customize for different party configurations before web bundling through a setting in the team yaml file
    - New web bundle outputs for all agents (analyst, architect, dev, pm, sm, tea, tech-writer, ux-designer, game-*, creative-squad)

    Phase 4 Workflow Updates (In Progress):

    - Initiated shift to separate phase 4 implementation artifacts from documentation
        - Phase 4 implementation artifacts (stories, code review, sprint plan, context files) will move to dedicated location outside docs folder
        - Installer questions and configuration added for artifact path selection
        - Updated workflow.yaml files for code-review, sprint-planning, story-context, epic-tech-context, and retrospective workflows to support this, but still might require some udpates

    Additional Changes:

    - New agent and action command header models for standardization
    - Enhanced web-bundle-activation-steps fragment
    - Updated web-bundler.js to support new structure
    - VS Code settings updated for new .bmad directory
    - Party mode instructions and workflow enhanced for better orchestration

   IDE Installer Updates:

    - Show version number of installer in cli
    - improved Installer UX
    - Gemini TOML Improved to have clear loading instructions with @ commands
    - All tools agent launcher mds improved to use a central file template critical indication isntead of hardcoding in 2 different locations.

.bmad/bmm/workflows/testarch/framework/workflow.yaml

@@ -0,0 +1,53 @@
+# Test Architect workflow: framework
+name: testarch-framework
+description: "Initialize production-ready test framework architecture (Playwright or Cypress) with fixtures, helpers, and configuration"
+author: "BMad"
+
+# Critical variables from config
+config_source: "{project-root}/.bmad/bmm/config.yaml"
+output_folder: "{config_source}:output_folder"
+user_name: "{config_source}:user_name"
+communication_language: "{config_source}:communication_language"
+document_output_language: "{config_source}:document_output_language"
+date: system-generated
+
+# Workflow components
+installed_path: "{project-root}/.bmad/bmm/workflows/testarch/framework"
+instructions: "{installed_path}/instructions.md"
+validation: "{installed_path}/checklist.md"
+
+# Variables and inputs
+variables:
+  test_dir: "{project-root}/tests" # Root test directory
+  use_typescript: true # Prefer TypeScript configuration
+  framework_preference: "auto" # auto, playwright, cypress - user can override auto-detection
+  project_size: "auto" # auto, small, large - influences framework recommendation
+
+# Output configuration
+default_output_file: "{test_dir}/README.md" # Main deliverable is test setup README
+
+# Required tools
+required_tools:
+  - read_file # Read package.json, existing configs
+  - write_file # Create config files, helpers, fixtures, tests
+  - create_directory # Create test directory structure
+  - list_files # Check for existing framework
+  - search_repo # Find architecture docs
+
+# Recommended inputs
+recommended_inputs:
+  - package_json: "package.json with project dependencies and scripts"
+  - architecture_docs: "Architecture or tech stack documentation (optional)"
+  - existing_tests: "Existing test files to detect current framework (optional)"
+
+tags:
+  - qa
+  - setup
+  - test-architect
+  - framework
+  - initialization
+
+execution_hints:
+  interactive: false # Minimize prompts; auto-detect when possible
+  autonomous: true # Proceed without user input unless blocked
+  iterative: true